SHAURYA KHURANA

‘To try, invites failure’

University of South Dakota

About me

I'm a Soft|

I have a MS degree in Computer Science and 4+ years of professional experience in working towards data analysis and defining data-driven models for actionable insights. I have a strong mathematical background with analytical and problem-solving skills. I excel in automating back-end processes, gathering raw data by utilizing APIs, and defining Machine Learning models with visual animations. My experience at USD, Zenatix, and Cognizant make me versatile in working independently as well as a team player.

Download my resumé Verify my Certifications

Interests

Machine Learning and Artificial Intelligence
Trend Analysis and Predictive Analytics
Data Science and Information Visualization
Statistical Modeling and Feature Engineering
Data Structures & Algorithms
Web Scraping and Data Mining
Computer Vision techniques and Deep Learning models

Education

MS in Computer Science, 2020
University of South Dakota
BTech in Electronics & Telecommunications, 2016
Jaypee Institute of Information Technology
80+ certifications via Coursera, 2012 - 2021
Esteemed universities and organizations

Building Data Pipelines

Tech Stack

Python

Markdown

Matplotlib

Seaborn

Sympy

Numpy

Django

Tableau

Statsmodels

Scikit Learn

SQL

AWS

Elasticsearch

HTML

Git

Docker

Jira

Linux

Ubuntu

Github

Trello

Experience

Graduate Research Assistant

University of South Dakota

Jan 2020 – Present Vermillion, SD

Leveraged Smartsheets API to programmatically access hierarchical data and transformed it into a user-interactive dashboard for biomedical researchers.
Invented a Python library REMAP to structure and sync data with Elasticsearch.
Designed a data mining workflow for Biofilm Data & Information Discovery System.
Built a web application 2DMatchecker in Streamlit for computing the characteristics of 2D materials using Logistic Regression and k-Means clustering.
Implemented an authentication gateway for Globus platform using Python SDK.

Data Analyst

Zenatix

Feb 2019 – Dec 2019 Gurgaon, India

Exploratory data analysis - analyzed unstructured big-time-series by data normalization, identified use cases and benchmarked data by statistical testing, and detected anomalies by information visualizations for scalability across customers.
Forecasted data like Energy Consumption, Energy Savings, Equipment Failures, Controller Health with over 95% accuracy using Fourier Transforms and ARIMA.
Deployed a k-Nearest Neighbors model to classify appliances and scheduled time-based and temperature-based controls on them for reducing costs up to 30%.
Streamed data by removing inconsistencies and structured it into metrics.
Introduced a data extracting tool (DWYW) using ipywidgets for account managers.
Refactored code by modularizing programs in Django to clean and improve its internal structure and speed up development time in the long run.

Beta Tester & Mentor

Coursera

Aug 2017 – Present Remote

Testing online courses before their launch, and ensuring proper content including videos, audio, quizzes, and assignments.
Providing feedback to course instructors to make sure the finished course is of high quality and free from errors. Tested 15+ courses and provided useful feedback.
Mentoring learners worldwide with their issues and guiding them with career track.
Actively participating in Discussion Forums for answering general queries and exploring new ideas.

Programmer Analyst

Cognizant

Nov 2016 – Feb 2019 Hyderabad, India

Integrated multiple sources of leases data into one system using Pandas and SQL.
Developed a dashboard in Streamlit to capture all customer’s change requests.
Accelerated Business intelligence reporting to assist with purchase-versus-leasing decisions by utilizing IBM TRIRIGA SaaS, Python SciPy stack, and Tableau.
Automated the process of loading leases data (.DIF files), reducing the time by 70%.
Upgraded the KLT framework to fetch customer surveys by designing REST APIs, and mapped feedback into the application by incorporating the Agile approach.
Innovated a data-driven model to determine the employee’s incentive from tickets.
Created Application, Database, Process, and BIRT servers in PROD and UAT environments for new clients using AMIs, CloudFormation, and Puppet.
Designed auto-generated daily email reports like Disk Usage, Server States, and CPU monitoring with detailed analytics for management using Seaborn and Dynatrace.
Expanded classification of log errors using regular expressions and defined user usage statistics across multiple servers, to speed up hotfixes and patching by 80%.